© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 63812
    Prev
    Next
    INDEX
    Explanations

    code/punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¾Ģ
    -0.25
     "<?
    -0.24
     clown
    -0.24
    æĸĩåĮĸèĬĤ
    -0.24
     stabbed
    -0.23
     hotter
    -0.23
    âĶħ
    -0.23
    æģIJæĢĸ
    -0.23
     mop
    -0.23
    æĮĩ导æĦıè§ģ
    -0.23
    POSITIVE LOGITS
    æĸ¼æĺ¯
    0.28
     updateUser
    0.28
    åıĪè¦ģ
    0.26
    Pres
    0.25
    让å®ĥ
    0.24
    gb
    0.24
    äºİæĺ¯
    0.24
    SAN
    0.23
    allowed
    0.23
     Sed
    0.23
    Activations Density 65.499%

    No Known Activations